[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-529341-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-529341-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","naplan-online-automated-scoring-research-program-research-report","NAPLAN Online Automated Scoring Research Program - Research Report","","NAPLAN Online automated scoring research program report detailing the National Assessment Program – Literacy and Numeracy (NAPLAN) Online approach developed and led by ACARA in collaboration with Pacific Metrics. The study evaluates feasibility and validity of automated scoring for NAPLAN writing using CRASE® and industry standards, comparing consistency with human markers. Evidence is drawn from over 11,000 essays across persuasive and narrative prompts, examining measurement construct alignment, rubric design, manipulation resilience, and practical implementation considerations.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/naplan-online-automated-scoring-research-program-research-report/529341/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/naplan-online-automated-scoring-research-program-research-report/529341.png","ImageObject",300,407,{"name":42,"@type":43},"Blitz","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-15","2026-10-09",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the purpose of the NAPLAN Online automated scoring research program?","Question",{"text":63,"@type":64},"To present details of the program and report key outcomes, focusing on evidence for the feasibility and validity of automated scoring for NAPLAN writing assessments.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was CRASE® evaluated in the report?",{"text":68,"@type":64},"The research used a nationally stratified sample of more than 11,000 essays and industry and research standards to compare CRASE® scoring consistency against scoring by human markers.",{"name":70,"@type":61,"acceptedAnswer":71},"What does the report say about reliability, consistency, and resistance to score manipulation?",{"text":72,"@type":64},"The tested modern automated scoring system showed the same level of reliability and consistency as scores produced by two independent human marker sets, and CRASE® was resilient to attempts to manipulate marking.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},529341,1791710505,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145},24464137899374,"https://us-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","NAPLAN ONLINE AUTOMATED SCORING RESEARCH PROGRAM:  \nRESEARCH REPORT  \nDr Goran Lazendic, Julie-Anne Justus and Dr Stanley Rabinowitz  \nExecutive summary  \nThe purpose of this paper is to present details of the National Assessment Program – Literacy and Numeracy ( NAPLAN) Online automated scoring research program and its key outcomes. The research program, developed and led by ACARA, was conducted in collaboration with Pacific Metrics, the provider of the Constructed-Response Automated Scoring Engine (CRASE®) .  \nThe research is designed to collect and evaluate empirical evidence on the feasibility and validity of automated scoring for NAPLAN writing assessments , based on a range of studies and analyses. The studies and analyses presented in this report used a broad, nationally stratified sample of over 11,000 essays across eight persuasive and four narrative writing prompts. Current industry and research standards were used to evaluate the performance of CRASE® to determine whether its scoring is consistent with that provided by human markers. The research also focused on some of the key aspects of NAPLAN writing assessments and whether its underlying measurement construct, including the design and implementation of the NAPLAN marking rubric , is conducive to automated scoring. Finally, the research investigated some of the practical issues of potential implementation of automated scoring.  \nResearch findings demonstrated that the modern automated scoring system tested, when marking NAPLAN writing, provided the same level of reliability and consistency as that found between two independent sets of human markers. Further results showed that CRASE® was resilient to attempts to manipulate marking and that the latent structure of automated scores was the same as that of the human markers.  \nAcknowledgements  \nMartina Bovell and Ross Bindon (ACARA) , and Dr Susan Lottridge and Dr Scott Wood ( Pacific Metrics) contributed their expertise, initiative and effort to the successful implementation and execution of the NAPLAN Online automated scoring research program. Most statistical analyses reported in this report were completed by Pacific Metric in collaboration with ACARA. ACARA also thanks members of its Measurement Advisory Group (MAG) for their valuable feedback on this report.  \nIntroduction  \nThe National Assessment Program – Literacy and Numeracy (NAPLAN) is an annual assessment of reading, writing, convention of language and numeracy for all students in Years 3, 5, 7 and 9. The assessments are undertaken nationwide in May, after the end of the first three months of a school year. The purpose of the administration of NAPLAN tests this early in a school year is to provide data as early as possible so that these data can be used to improve student learning outcomes. One of the criticisms of NAPLAN is that the results of the current paper-based tests are released too late in a school year to be effectively used to inform and support teaching and learning.  \nIn addition to providing better and more precise assessment, moving NAPLAN online will significantly shorten the time needed to provide results to schools and students by removing the administrative and logistic burden of processing millions of paper tests and conducting longitudinal equating of NAPLAN assessment scales prior to administering the tests in May. During the agreed transition period, schools that switch to NAPLAN Online will receive a first set of their test results three weeks after the online test window is closed. The turnaround of NAPLAN results could be reduced to several days. The new online and adaptive NAPLAN tests in reading, conventions of language and numeracy will be computer-scored as a student progresses through the tests , allowing drastically reduced time to provide results and feedback on the NAPLAN online tests.  \nMarking of NAPLAN writing tests is currently a large logistical operation that takes several months and requires significant resources","cbCaipD1e6aYOLqF","https://ap.wps.com/l/cbCaipD1e6aYOLqF","pdf",1198090,77,"English","# Executive summary\n# Acknowledgements\n# Introduction\n## NAPLAN overview and rationale for online delivery\n## Automated scoring for NAPLAN writing\n## Measurement construct and validity considerations","[{\"question\":\"What is the purpose of the NAPLAN Online automated scoring research program?\",\"answer\":\"To present details of the program and report key outcomes, focusing on evidence for the feasibility and validity of automated scoring for NAPLAN writing assessments.\"},{\"question\":\"How was CRASE® evaluated in the report?\",\"answer\":\"The research used a nationally stratified sample of more than 11,000 essays and industry and research standards to compare CRASE® scoring consistency against scoring by human markers.\"},{\"question\":\"What does the report say about reliability, consistency, and resistance to score manipulation?\",\"answer\":\"The tested modern automated scoring system showed the same level of reliability and consistency as scores produced by two independent human marker sets, and CRASE® was resilient to attempts to manipulate marking.\"}]","NAPLAN Online Automated Scoring Research Program - Research Report | PDF",1791520970,194]